Packaging & Memory

Chiplets, 3D IC, HBM stacks, DDR5/PCIe lanes, and bandwidth tradeoffs.

  • 25 Tracked terms
  • Last 30 days Feed window

What this topic collects on

An article joins this feed when it matches these terms. Each one is also a search of its own.

Latest in Packaging & Memory

CHOSUNBIZ
biz.chosun.com > en > en-it > 09/14/2026 > 52TBQREJFBCPHOPGMIPCVMD26Y

SK hynix deepens TSMC ties for 3D DRAM, diverges from Samsung

6+ hour, 51+ min ago   (471+ words) Hynix pursues logic-foundry DRAM approach with TSMC links while Samsung stays in-house According to the semiconductor industry on the 14th, SK hynix, at the "2026 Future Forum" held on the 8th at the Icheon Campus in Gyeonggi Province, presented as the main directions…...

TrendForce
trendforce.com > news > 09/14/2026 > news-kepler-claims-hbm-alternative-without-euv-using-globalfoundries-28nm-fabs-2027-production

[News] Kepler Claims HBM Alternative Without EUV Using GlobalFoundries’ 28nm Fabs, 2027 Production

14+ hour, 35+ min ago   (281+ words) As the AI boom strains supply and pushes up costs, startups are exploring new ways to expand memory production. According to TechPowerUp, Kepler Computing claims to have developed an alternative approach to HBM based on a new 3D stacking technique and…...

DIGITIMES
digitimes.com > news > a20/26/0914VL214 > talent-nand-hbm-design-flash.html

Sandisk recruits engineers in Korea as memory talent race heats up

12+ hour, 8+ min ago   (147+ words) digitimes Sandisk recruits engineers in Korea as memory talent race heats up Sandisk Vice President Rajeev Nagabhirava discusses AI memory architecture at the SEMICON Taiwan 2026 Memory Summit. Credit: Sherri Wang Sandisk is making an unusual push into engineering recruitment in…...

Techmeme
techmeme.com > 260913 > p19

Document: Samsung and SK Hynix rejected KEPCO's proposal to prepay ~$18.7B of chip cluster power bills, citing uncertainty over long-term chip demand

13+ hour, 7+ min ago   (12+ words) Top news and commentary for technology's leaders, from all around the web....

SemiAnalysis
newsletter.semianalysis.com > p > long-live-the-short-king-why-4-hi

Long Live the Short King: Why 4-hi HBM Wins

17+ hour, 45+ min ago   (571+ words) This report will go through the reasoning behind what’s changed in the capacity equation, demonstrate that often HBM capacity is stranded, and show how this can be a win-win for both labs’ TCO and memory supplier profitability. HBM has been…...

Seoul Economic Daily
en.sedaily.com > technology > 09/13/2026 > korea-moves-to-localize-optical-tech-for-ai-data-centers

Korea Moves to Localize Optical Tech for AI Data Centers

19+ hour ago   (360+ words) Seoul Economic Daily The South Korean government is moving to localize optical communication technology for artificial intelligence data centers, or AIDCs As AI data centers grow larger, how quickly tens of thousands of graphics processing units can be connected has…...

Medium
medium.com > @cse20/16/0007 > the-local-ai-hardware-trap-why-vram-bandwidth-and-resale-value-matter-more-than-benchmarks-e5f4f791fcc5

The Local AI Hardware Trap: Why VRAM, Bandwidth, and Resale Value Matter More Than Benchmarks

1+ day, 10+ min ago   (30+ words) Local AI hardware isn’t just about VRAM or benchmark scores. Discover how memory bandwidth, power …...

The Economic Times
m.economictimes.com > tech > technology > south-koreas-expanded-espionage-law-takes-effect-amid-push-to-protect-chip-technology > amp_articleshow > 134195142.cms

South Korea's expanded espionage law takes effect amid push to protect chip technology

1+ day, 5+ hour ago   (228+ words) Expenses keep rising. Build a second income with options selling. IGI operating at full capacity for scheduled flights, no diversion reported due to VVIP movements for BRICS Summit: Senior AAI official BRICS Summit 2026: Russian President Putin proposes new insurance mechanism…...

BENIN WEB TV
beninwebtv.bj > en > ai-d-matrix-adopts-nvidias-nvlink-fusion-for-its-raptor-accelerators

AI: d-Matrix adopts Nvidia's NVLink Fusion for its Raptor accelerators

4+ day, 19+ min ago   (327+ words) The American start-up d-Matrix will integrate Nvidia's NVLink Fusion technology into its future Raptor accelerators, designed to accelerate the inference of artificial intelligence models in data centers. The American start-up d-Matrix will integrate Nvidia’s NVLink Fusion technology into its next…...

CHOSUNBIZ
biz.chosun.com > en > en-it > 09/13/2026 > UJUB47GQIBFE3KBKSM3GVTTPD4

SanDisk expands Korea engineer hiring as AI boom fuels NAND race

1+ day, 10+ hour ago   (13+ words) CHOSUNBIZ Chosunbiz...